{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:30:35Z","timestamp":1770748235332,"version":"3.49.0"},"reference-count":56,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T00:00:00Z","timestamp":1628208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["2020.05711.BD"],"award-info":[{"award-number":["2020.05711.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/04436\/2020"],"award-info":[{"award-number":["UIDB\/04436\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDP\/04436\/2020"],"award-info":[{"award-number":["UIDP\/04436\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["NORTE-01-0145-FEDER-030386"],"award-info":[{"award-number":["NORTE-01-0145-FEDER-030386"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Machines"],"abstract":"<jats:p>Powered Assistive Devices (PADs) have been proposed to enable repetitive, user-oriented gait rehabilitation. They may include torque controllers that typically require reference joint torque trajectories to determine the most suitable level of assistance. However, a robust approach able to automatically estimate user-oriented reference joint torque trajectories, namely ankle torque, while considering the effects of varying walking speed, body mass, and height on the gait dynamics, is needed. This study evaluates the accuracy and generalization ability of two Deep Learning (DL) regressors (Long-Short Term Memory and Convolutional Neural Network (CNN)) to generate user-oriented reference ankle torque trajectories by innovatively customizing them according to the walking speed (ranging from 1.0 to 4.0 km\/h) and users\u2019 body height and mass (ranging from 1.51 to 1.83 m and 52.0 to 83.7 kg, respectively). Furthermore, this study hypothesizes that DL regressors can estimate joint torque without resourcing electromyography signals. CNN was the most robust algorithm (Normalized Root Mean Square Error: 0.70 \u00b1 0.06; Spearman Correlation: 0.89 \u00b1 0.03; Coefficient of Determination: 0.91 \u00b1 0.03). No statistically significant differences were found in CNN accuracy (p-value &gt; 0.05) whether electromyography signals are included as inputs or not, enabling a less obtrusive and accurate setup for torque estimation.<\/jats:p>","DOI":"10.3390\/machines9080154","type":"journal-article","created":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T21:49:41Z","timestamp":1628459381000},"page":"154","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Kinematics, Speed, and Anthropometry-Based Ankle Joint Torque Estimation: A Deep Learning Regression Approach"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-7409","authenticated-orcid":false,"given":"Lu\u00eds","family":"Moreira","sequence":"first","affiliation":[{"name":"Center for MicroElectroMechanical Systems (CMEMS), University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9547-3051","authenticated-orcid":false,"given":"Joana","family":"Figueiredo","sequence":"additional","affiliation":[{"name":"Center for MicroElectroMechanical Systems (CMEMS), University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4109-2939","authenticated-orcid":false,"given":"Jo\u00e3o Paulo","family":"Vilas-Boas","sequence":"additional","affiliation":[{"name":"Faculty of Sport, CIFI2D, and Porto Biomechanics Laboratory (LABIOMEP), University of Porto, 4200-450 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-7203","authenticated-orcid":false,"given":"Cristina Peixoto","family":"Santos","sequence":"additional","affiliation":[{"name":"Center for MicroElectroMechanical Systems (CMEMS), University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Johnson, W., Onuma, O., Owolabi, M., Sachdev, S., and Bulletin of World Health Organization (2019, June 05). Stroke: A Global Response Is Needed. Available online: https:\/\/www.who.int\/bulletin\/volumes\/94\/9\/16-181636\/en\/.","DOI":"10.2471\/BLT.16.181636"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/S1474-4422(19)30034-1","article-title":"Global, regional, and national burden of stroke, 1990\u20132016: A systematic analysis for the Global Burden of Disease Study 2016","volume":"18","author":"Johnson","year":"2019","journal-title":"Lancet Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10198-018-0984-0","article-title":"Economic burden of stroke: A systematic review on post-stroke care","volume":"20","author":"Rajsic","year":"2019","journal-title":"Eur. J. Health Econ."},{"key":"ref_4","first-page":"17","article-title":"The Economic Impact of Stroke in Europe: Current Costs of Stroke throughout Europe","volume":"5","author":"Leal","year":"2019","journal-title":"Eur. Stroke J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.3389\/fphys.2018.01021","article-title":"Post-stroke Hemiplegic Gait: New Perspective and Insights","volume":"9","author":"Li","year":"2018","journal-title":"Front. Physiol."},{"key":"ref_6","unstructured":"Da Sa\u00fade, D.G. (2021, August 04). Programa Nacional de Preven\u00e7\u00e3o e Controlo das Doen\u00e7as Cardiovasculares. Dgs. Available online: https:\/\/www.google.pt\/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwin1rHhmc3MAhUDuhoKHYOvAe4QFggiMAA&url=http:\/\/1nj5ms2lli5hdggbe3mm7ms5.wpengine.netdna-cdn.com\/files\/2015\/08\/Programa-Nacional-de-Prevencao-das-Doencas-Cardiovasculare."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1743-0003-12-1","article-title":"Control strategies for active lower extremity prosthetics and orthotics: A review","volume":"12","author":"Tucker","year":"2015","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/TMECH.2012.2219065","article-title":"An Adaptive Wearable Parallel Robot for the Treatment of Ankle Injuries","volume":"19","author":"Jamwal","year":"2012","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.mechatronics.2015.04.005","article-title":"Recent development of mechanisms and control strategies for robot-assisted lower limb rehabilitation","volume":"31","author":"Meng","year":"2015","journal-title":"Mechatronics"},{"key":"ref_10","unstructured":"Figueiredo, J.S.C. (2019). Smart wearable orthosis to assist impaired human walking. [Ph.D. Thesis, University of Minho]."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1109\/TRO.2008.926860","article-title":"A Human--Exoskeleton Interface Utilizing Electromyography","volume":"24","author":"Fleischer","year":"2008","journal-title":"IEEE Trans. Robot."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hassani, W., Mohammed, S., Rifai, H., and Amirat, Y. (2013, January 3\u20137). EMG based approach for wearer-centered control of a knee joint actuated orthosis. Proceedings of the 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan.","DOI":"10.1109\/IROS.2013.6696471"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hassani, W., Mohammed, S., and Amirat, Y. (2013, January 24\u221228). Real-Time EMG Driven Lower Limb Actuated Orthosis for Assistance as Needed Movement Strategy. Proceedings of the Robotics: Science and Systems 2013, Berlin, Germany.","DOI":"10.15607\/RSS.2013.IX.054"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.conengprac.2014.02.002","article-title":"Powered orthosis for lower limb movements assistance and rehabilitation","volume":"26","author":"Hassani","year":"2014","journal-title":"Control. Eng. Pract."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cheah, C.C., and Collins, S.H. (2015, January 26\u201330). Experimental comparison of torque control methods on an ankle exoskeleton during human walking. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139980"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1016\/j.jbiomech.2014.01.037","article-title":"Speed-dependent reference joint trajectory generation for robotic gait support","volume":"47","author":"Koopman","year":"2014","journal-title":"J. Biomech."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1007\/s11517-013-1076-z","article-title":"A real-time system for biomechanical analysis of human movement and muscle function","volume":"51","author":"Bogert","year":"2013","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1016\/j.gaitpost.2010.08.009","article-title":"A multiple-task gait analysis approach: Kinematic, kinetic and EMG reference data for healthy young and adult subjects","volume":"33","author":"Bovi","year":"2011","journal-title":"Gait Posture"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/s41597-019-0323-z","article-title":"Human kinematic, kinetic and EMG data during different walking and stair ascending and descending tasks","volume":"6","author":"Lencioni","year":"2019","journal-title":"Sci. Data"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e918","DOI":"10.7717\/peerj.918","article-title":"An elaborate data set on human gait and the effect of mechanical perturbations","volume":"3","author":"Moore","year":"2015","journal-title":"PeerJ"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2014\/527940","article-title":"Biomechanics of Gait during Pregnancy","volume":"2014","author":"Branco","year":"2014","journal-title":"Sci. World J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/S0966-6362(02)00060-7","article-title":"Predicting peak kinematic and kinetic parameters from gait speed","volume":"17","author":"Lelas","year":"2003","journal-title":"Gait Posture"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11517-019-02061-3","article-title":"Prediction of lower limb joint angles and moments during gait using artificial neural networks","volume":"58","author":"Mundt","year":"2019","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1016\/j.jbiomech.2008.03.015","article-title":"The effect of walking speed on the gait of typically developing children","volume":"41","author":"Schwartz","year":"2008","journal-title":"J. Biomech."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1590\/2446-4740.180017","article-title":"Biomechanical alterations of gait on overweight subjects","volume":"34","author":"Silva","year":"2018","journal-title":"Res. Biomed. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neucli.2008.02.002","article-title":"Effect of speed on kinematic, kinetic, electromyographic and energetic reference values during treadmill walking","volume":"38","author":"Stoquart","year":"2008","journal-title":"Neurophysiol. Clin. Neurophysiol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.gaitpost.2009.11.011","article-title":"Differences in self-selected and fastest-comfortable walking in post-stroke hemiparetic persons","volume":"31","author":"Beaman","year":"2010","journal-title":"Gait Posture"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Smith, A.J.J., Lemaire, E.D., and Nantel, J. (2018). Lower limb sagittal kinematic and kinetic modeling of very slow walking for gait trajectory scaling. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0203934"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"185","DOI":"10.2478\/s13230-012-0007-2","article-title":"Investigating improvements to neural network based EMG to joint torque estimation","volume":"2","author":"Chandrapal","year":"2011","journal-title":"Paladyn J. Behav. Robot."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1016\/j.jbiomech.2006.04.014","article-title":"Feasibility of estimating isokinetic knee torque using a neural network model","volume":"40","author":"Hahn","year":"2007","journal-title":"J. Biomech."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TNSRE.2010.2047592","article-title":"A Muscle-Reflex Model That Encodes Principles of Legged Mechanics Produces Human Walking Dynamics and Muscle Activities","volume":"18","author":"Geyer","year":"2010","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.gaitpost.2020.01.021","article-title":"Adaptive predictive systems applied to gait analysis: A systematic review","volume":"77","author":"Caldas","year":"2020","journal-title":"Gait Posture"},{"key":"ref_33","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: A review","volume":"33","author":"Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Skansi, S. (2018). Introduction to Deep Learning: From Logical Calculus to Artificial Intelligence, Springer.","DOI":"10.1007\/978-3-319-73004-2"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"362","DOI":"10.3389\/fbioe.2020.00362","article-title":"Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks","volume":"8","author":"Zaroug","year":"2020","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Moreira, L., Cerqueira, S., Figueiredo, J., Vilas-Boas, J., and Santos, C. (2020, January 15\u201317). AI-based Reference Ankle Joint Torque Trajectory Generation for Robotic Gait Assistance: First Steps. Proceedings of the 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), Ponta Delgada, Portugal.","DOI":"10.1109\/ICARSC49921.2020.9096205"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.pmrj.2013.12.017","article-title":"Gait Disturbances in Patients with Stroke","volume":"6","author":"Balaban","year":"2014","journal-title":"PM&R"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2480","DOI":"10.1109\/TMECH.2017.2755048","article-title":"Real-Time Hybrid Locomotion Mode Recognition for Lower Limb Wearable Robots","volume":"22","author":"Parri","year":"2017","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1729881417730321","DOI":"10.1177\/1729881417730321","article-title":"Kinematic-based locomotion mode recognition for power augmentation exoskeleton","volume":"14","author":"Kim","year":"2017","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, Z., Ning, Z., Zhang, Y., Liu, Y., Cao, W., Wu, X., and Chen, C. (2020). A Novel Motion Intention Recognition Approach for Soft Exoskeleton via IMU. Electronics, 9.","DOI":"10.3390\/electronics9122176"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Gong, C., Xu, D., Zhou, Z., Vitiello, N., and Wang, Q. (2018, January 6\u20139). Real-Time On-Board Recognition of Locomotion Modes for an Active Pelvis Orthosis. Proceedings of the 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), Beijing, China.","DOI":"10.1109\/HUMANOIDS.2018.8625044"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"99","DOI":"10.4218\/etrij.14.0113.0064","article-title":"Real-Time Locomotion Mode Recognition Employing Correlation Feature Analysis Using EMG Pattern","volume":"36","author":"Kim","year":"2014","journal-title":"ETRI J."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1097\/00002060-199801000-00002","article-title":"Gender differences in joint biomechanics during walking Normative Study in Young Adults","volume":"77","author":"Kerrigan","year":"1998","journal-title":"Am. J. Phys. Med. Rehabil."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1093\/nutrit\/nuv105","article-title":"Adult height, nutrition, and population health","volume":"74","author":"Perkins","year":"2016","journal-title":"Nutr. Rev."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/S1050-6411(00)00027-4","article-title":"Development of recommendations for SEMG sensors and sensor placement procedures","volume":"10","author":"Hermens","year":"2000","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1038\/s41597-021-00881-3","article-title":"Lower limb kinematic, kinetic, and EMG data from young healthy humans during walking at controlled speeds","volume":"8","author":"Moreira","year":"2021","journal-title":"Sci. Data"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1186\/1475-925X-9-72","article-title":"Evaluation of EMG processing techniques using Information Theory","volume":"9","author":"Politti","year":"2010","journal-title":"Biomed. Eng. Online"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1177\/0954411919827033","article-title":"The LAMB gait analysis protocol: Definition and experimental assessment of operator-related variability","volume":"233","author":"Rabuffetti","year":"2019","journal-title":"Proc. Inst. Mech. Eng. Part H J. Eng. Med."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Perry, J. (1992). Gait Analysis: Normal and Pathological Function, SLACK Incorporated.","DOI":"10.1097\/01241398-199211000-00023"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Su, B., and Gutierrez-Farewik, E.M. (2020). Gait Trajectory and Gait Phase Prediction Based on an LSTM Network. Sensors, 20.","DOI":"10.3390\/s20247127"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Liu, G., Zhang, L., Han, B., Zhang, T., Wang, Z., and Wei, P. (2019, January 22\u201326). sEMG-Based Continuous Estimation of Knee Joint Angle Using Deep Learning with Convolutional Neural Network. Proceedings of the 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), Vancouver, BC, Canada.","DOI":"10.1109\/COASE.2019.8843168"},{"key":"ref_53","first-page":"335","article-title":"Lessons in biostatistics","volume":"25","author":"Breslow","year":"2014","journal-title":"Past Present Future Stat. Sci."},{"key":"ref_54","first-page":"261","article-title":"A marcha no paciente hemipar\u00e9tico","volume":"3","author":"Silva","year":"2005","journal-title":"Universitas: Ci\u00eancias da Sa\u00fade"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.gaitpost.2005.10.007","article-title":"Prediction methods to account for the effect of gait speed on lower limb angular kinematics","volume":"24","author":"Hanlon","year":"2006","journal-title":"Gait Posture"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1016\/j.jbiomech.2010.01.027","article-title":"Filtering the surface EMG signal: Movement artifact and baseline noise contamination","volume":"43","author":"Gilmore","year":"2010","journal-title":"J. Biomech."}],"container-title":["Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1702\/9\/8\/154\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:42:04Z","timestamp":1760164924000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1702\/9\/8\/154"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,6]]},"references-count":56,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["machines9080154"],"URL":"https:\/\/doi.org\/10.3390\/machines9080154","relation":{},"ISSN":["2075-1702"],"issn-type":[{"value":"2075-1702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,6]]}}}